import pandas as pd
import seaborn as sns
import plotly.express as px
import numpy as np
import matplotlib.pyplot as plt
import plotly.io as pio
pio.renderers.default = "plotly_mimetype+notebook"
For this excercise, we have written the following code to load the stock dataset built into plotly express.
stocks = px.data.stocks()
stocks.head()
| date | GOOG | AAPL | AMZN | FB | NFLX | MSFT | |
|---|---|---|---|---|---|---|---|
| 0 | 2018-01-01 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 1.000000 | 1.000000 |
| 1 | 2018-01-08 | 1.018172 | 1.011943 | 1.061881 | 0.959968 | 1.053526 | 1.015988 |
| 2 | 2018-01-15 | 1.032008 | 1.019771 | 1.053240 | 0.970243 | 1.049860 | 1.020524 |
| 3 | 2018-01-22 | 1.066783 | 0.980057 | 1.140676 | 1.016858 | 1.307681 | 1.066561 |
| 4 | 2018-01-29 | 1.008773 | 0.917143 | 1.163374 | 1.018357 | 1.273537 | 1.040708 |
Select a stock and create a suitable plot for it. Make sure the plot is readable with relevant information, such as date, values.
# YOUR CODE HERE
plt.figure(figsize=(12,8))
plt.plot(stocks["date"], stocks["AAPL"])
plt.xlabel("Date")
plt.ylabel("Stock value")
plt.title("Apple Stock")
plt.xticks(stocks["date"].array[::20]);
You've already plot data from one stock. It is possible to plot multiples of them to support comparison.
To highlight different lines, customise line styles, markers, colors and include a legend to the plot.
# YOUR CODE HERE
plt.figure(figsize=(12,8))
plt.plot(stocks["date"], stocks["GOOG"], label="GOOG")
plt.plot(stocks["date"], stocks["AAPL"], label="AAPL")
plt.plot(stocks["date"], stocks["AMZN"], label="AMZN")
plt.plot(stocks["date"], stocks["FB"], label="FB")
plt.plot(stocks["date"], stocks["NFLX"], label="NFLX")
plt.plot(stocks["date"], stocks["MSFT"], label="MSFT")
plt.xlabel("Date")
plt.ylabel("Stock value")
plt.title("Stocks")
plt.legend()
plt.xticks(stocks["date"].array[::20]);
First, load the tips dataset
tips = sns.load_dataset('tips')
tips.head()
| total_bill | tip | sex | smoker | day | time | size | |
|---|---|---|---|---|---|---|---|
| 0 | 16.99 | 1.01 | Female | No | Sun | Dinner | 2 |
| 1 | 10.34 | 1.66 | Male | No | Sun | Dinner | 3 |
| 2 | 21.01 | 3.50 | Male | No | Sun | Dinner | 3 |
| 3 | 23.68 | 3.31 | Male | No | Sun | Dinner | 2 |
| 4 | 24.59 | 3.61 | Female | No | Sun | Dinner | 4 |
Let's explore this dataset. Pose a question and create a plot that support drawing answers for your question.
Some possible questions:
# YOUR CODE HERE
# Do group size have a positive correlation with tips?
sns.scatterplot(data=tips, x="size", y="tip")
corr = tips["size"].corr(tips["tip"])
print(f"Correlation between group size and tips are {corr:.2f}")
# Conclusion there is a possitive correlation between the group size and tip size but it's rather weak 0.5. Preferably we need more data about larger group sizes.
Correlation between group size and tips are 0.49
Redo the above exercises (challenges 2 & 3) with plotly express. Create diagrams which you can interact with.
Hints:
# YOUR CODE HERE
px.line(stocks, x="date", y=["GOOG", "AAPL", "AMZN", "FB", "NFLX", "MSFT"], labels={"date": "Date", "value": "Stock value", "variable": "Stocks"}, height=600)
# YOUR CODE HERE
px.scatter(tips, x="total_bill", y="tip", color="sex", facet_col="smoker", facet_row="time", height=600)
Recreate the barplot below that shows the population of different continents for the year 2007.
Hints:
#load data
df = px.data.gapminder()
df.head()
| country | continent | year | lifeExp | pop | gdpPercap | iso_alpha | iso_num | |
|---|---|---|---|---|---|---|---|---|
| 0 | Afghanistan | Asia | 1952 | 28.801 | 8425333 | 779.445314 | AFG | 4 |
| 1 | Afghanistan | Asia | 1957 | 30.332 | 9240934 | 820.853030 | AFG | 4 |
| 2 | Afghanistan | Asia | 1962 | 31.997 | 10267083 | 853.100710 | AFG | 4 |
| 3 | Afghanistan | Asia | 1967 | 34.020 | 11537966 | 836.197138 | AFG | 4 |
| 4 | Afghanistan | Asia | 1972 | 36.088 | 13079460 | 739.981106 | AFG | 4 |
# YOUR CODE HERE
data = df[df["year"] == 2007]
cont = data["continent"].unique()
pop = np.zeros(len(cont))
for i in range(len(cont)):
pop[i] = data[data["continent"] == cont[i]]["pop"].sum()
fig = px.bar(x=pop, y=cont, color=cont, title="Population per continent in 2007", labels={"x": "Population", "y": "Continent", "color": "Continents"})
fig.update_yaxes(categoryorder="total descending")
fig.show()